Direct acoustics-to-word (A2W) systems for end-to-end automatic
speech recognition are simpler to train, and more efficient to decode
with, than sub-word systems. However, A2W systems can have difficulties at training time when data is limited, and at decoding time
when recognizing words outside the training vocabulary. To address
these shortcomings, we investigate the use of recently proposed acoustic and acoustically grounded word embedding techniques in A2W
systems. The idea is based on treating the final pre-softmax weight
matrix of an AWE recognizer as a matrix of word embedding vectors,
and using an externally trained set of word embeddings to improve
the quality of this matrix. In particular we introduce two ideas: (1)
Enforcing similarity at training time between the external embeddings
and the recognizer weights, and (2) using the word embeddings at
test time for predicting out-of-vocabulary words. Our word embedding model is acoustically grounded, that is it is learned jointly with
acoustic embeddings so as to encode the words’ acoustic-phonetic
content; and it is parametric, so that it can embed any arbitrary (potentially out-of-vocabulary) sequence of characters. We find that
both techniques improve the performance of an A2W recognizer on
conversational telephone speech.
more »
« less
Analyzing autoencoder-based acoustic word embeddings
Recent studies have introduced methods for learning acoustic word embeddings (AWEs)—fixed-size vector representations of words which encode their acoustic features. Despite the widespread use of AWEs in speech processing research, they have only been evaluated quantitatively in their ability to discriminate between whole word tokens. To better understand the applications of AWEs in various downstream tasks and in cognitive modeling, we need to analyze the representation spaces of AWEs. Here we analyze basic properties of AWE spaces learned by a sequence-to-sequence encoder-decoder model in six typologically diverse languages. We first show that these AWEs preserve some information about words’ absolute duration and speaker. At the same time, the representation space of these AWEs is organized such that the distance between words’ embeddings increases with those words’ phonetic dissimilarity. Finally, the AWEs exhibit a word onset bias, similar to patterns reported in various studies on human speech processing and lexical access. We argue this is a promising result and encourage further evaluation of AWEs as a potentially useful tool in cognitive science, which could provide a link between speech processing and lexical memory.
more »
« less
- Award ID(s):
- 1734245
- NSF-PAR ID:
- 10182737
- Date Published:
- Journal Name:
- ICLR Workshop on Bridging AI and Cognitive Science
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Learning to process speech in a foreign language involves learning new representations for mapping the auditory signal to linguistic structure. Behavioral experiments suggest that even listeners that are highly proficient in a non-native language experience interference from representations of their native language. However, much of the evidence for such interference comes from tasks that may inadvertently increase the salience of native language competitors. Here we tested for neural evidence of proficiency and native language interference in a naturalistic story listening task. We studied electroencephalography responses of 39 native speakers of Dutch (14 male) to an English short story, spoken by a native speaker of either American English or Dutch. We modeled brain responses with multivariate temporal response functions, using acoustic and language models. We found evidence for activation of Dutch language statistics when listening to English, but only when it was spoken with a Dutch accent. This suggests that a naturalistic, monolingual setting decreases the interference from native language representations, whereas an accent in the listener's own native language may increase native language interference, by increasing the salience of the native language and activating native language phonetic and lexical representations. Brain responses suggest that such interference stems from words from the native language competing with the foreign language in a single word recognition system, rather than being activated in a parallel lexicon. We further found that secondary acoustic representations of speech (after 200 ms latency) decreased with increasing proficiency. This may reflect improved acoustic–phonetic models in more proficient listeners.
Significance Statement Behavioral experiments suggest that native language knowledge interferes with foreign language listening, but such effects may be sensitive to task manipulations, as tasks that increase metalinguistic awareness may also increase native language interference. This highlights the need for studying non-native speech processing using naturalistic tasks. We measured neural responses unobtrusively while participants listened for comprehension and characterized the influence of proficiency at multiple levels of representation. We found that salience of the native language, as manipulated through speaker accent, affected activation of native language representations: significant evidence for activation of native language (Dutch) categories was only obtained when the speaker had a Dutch accent, whereas no significant interference was found to a speaker with a native (American) accent. -
more » « less
Abstract Partial speech input is often understood to trigger rapid and automatic activation of successively higher-level representations of words, from sound to meaning. Here we show evidence from magnetoencephalography that this type of incremental processing is limited when words are heard in isolation as compared to continuous speech. This suggests a less unified and automatic word recognition process than is often assumed. We present evidence from isolated words that neural effects of phoneme probability, quantified by phoneme surprisal, are significantly stronger than (statistically null) effects of phoneme-by-phoneme lexical uncertainty, quantified by cohort entropy. In contrast, we find robust effects of both cohort entropy and phoneme surprisal during perception of connected speech, with a significant interaction between the contexts. This dissociation rules out models of word recognition in which phoneme surprisal and cohort entropy are common indicators of a uniform process, even though these closely related information-theoretic measures both arise from the probability distribution of wordforms consistent with the input. We propose that phoneme surprisal effects reflect automatic access of a lower level of representation of the auditory input (e.g., wordforms) while the occurrence of cohort entropy effects is task sensitive, driven by a competition process or a higher-level representation that is engaged late (or not at all) during the processing of single words.
-
more » « less
Abstract Over the past few decades, research into the function of the cerebellum has expanded far beyond the motor domain. A growing number of studies are probing the role of specific cerebellar subregions, such as Crus I and Crus II, in higher-order cognitive functions including receptive language processing. In the current fMRI study, we show evidence for the cerebellum’s sensitivity to variation in two well-studied psycholinguistic properties of words—lexical frequency and phonological neighborhood density—during passive, continuous listening of a podcast. To determine whether, and how, activity in the cerebellum correlates with these lexical properties, we modeled each word separately using an amplitude-modulated regressor, time-locked to the onset of each word. At the group level, significant effects of both lexical properties landed in expected cerebellar subregions: Crus I and Crus II. The BOLD signal correlated with variation in each lexical property, consistent with both language-specific and domain-general mechanisms. Activation patterns at the individual level also showed that effects of phonological neighborhood and lexical frequency landed in Crus I and Crus II as the most probable sites, though there was activation seen in other lobules (especially for frequency). Although the exact cerebellar mechanisms used during speech and language processing are not yet evident, these findings highlight the cerebellum’s role in word-level processing during continuous listening.
-
more » « less
Abstract Speech processing often occurs amid competing inputs from other modalities, for example, listening to the radio while driving. We examined the extent to which dividing attention between auditory and visual modalities (bimodal divided attention) impacts neural processing of natural continuous speech from acoustic to linguistic levels of representation. We recorded electroencephalographic (EEG) responses when human participants performed a challenging primary visual task, imposing low or high cognitive load while listening to audiobook stories as a secondary task. The two dual-task conditions were contrasted with an auditory single-task condition in which participants attended to stories while ignoring visual stimuli. Behaviorally, the high load dual-task condition was associated with lower speech comprehension accuracy relative to the other two conditions. We fitted multivariate temporal response function encoding models to predict EEG responses from acoustic and linguistic speech features at different representation levels, including auditory spectrograms and information-theoretic models of sublexical-, word-form-, and sentence-level representations. Neural tracking of most acoustic and linguistic features remained unchanged with increasing dual-task load, despite unambiguous behavioral and neural evidence of the high load dual-task condition being more demanding. Compared to the auditory single-task condition, dual-task conditions selectively reduced neural tracking of only some acoustic and linguistic features, mainly at latencies >200 ms, while earlier latencies were surprisingly unaffected. These findings indicate that behavioral effects of bimodal divided attention on continuous speech processing occur not because of impaired early sensory representations but likely at later cognitive processing stages. Crossmodal attention-related mechanisms may not be uniform across different speech processing levels.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
